Fed-Batch Process Modelling for State Estimation and Optimal Control

An efficient and flexible parameter estimation scheme for grey-box models in the sense of systems of nonlinear discretely, partially observed Itô stochastic differential equations with measurement noise is presented along with a corresponding software implementation. The estimation scheme is based on the extended Kalman filter and features maximum likelihood as well as maximum a posteriori estimation on multiple independent data sets, including irregularly sampled data sets and data sets with occasional outliers and missing observations. The software implementation is compared to an existing software tool and proves to have superior estimation performance both in terms of quality of estimates and in terms of reproducibility. In particular, the new tool provides more accurate and consistent estimates of the parameters of the diffusion term.

[1]  David W. Clarke,et al.  Generalized Predictive Control - Part II Extensions and interpretations , 1987, Autom..

[2]  Denis Dochain,et al.  Adaptive Control of Fed-Batch Fermentation Processes , 1988 .

[3]  Henrik Madsen,et al.  A generalization of some classical time series tools , 2001 .

[4]  Heinz Unbehauen,et al.  Continuous-time approaches to system identification - A survey , 1990, Autom..

[5]  Sten Bay Jørgensen,et al.  A method for systematic improvement of stochastic grey-box models , 2004, Comput. Chem. Eng..

[6]  Roger B. Sidje,et al.  Expokit: a software package for computing matrix exponentials , 1998, TOMS.

[7]  S. Palanki,et al.  A feedback-based implementation scheme for batch process optimization , 2000 .

[8]  Heinz Unbehauen,et al.  A review of identification in continuous-time systems , 1998 .

[9]  J. A. Wilson,et al.  A hybrid neural network-first principles approach to batch unit optimisation , 1998 .

[10]  M. B. Zarrop,et al.  Book Review: Adaptive Optimal Control: the thinking man's GPC , 1991 .

[11]  G. Bierman.  Factorization methods for discrete sequential estimation , 1977 .

[12]  B. Speelpenning.  Compiling Fast Partial Derivatives of Functions Given by Algorithms , 1980 .

[13]  Sten Bay Jørgensen,et al.  A unified framework for systematic model improvement , 2003 .

[14]  Jan Nygaard Nielsen,et al.  Parameter estimation in stochastic differential equations: An overview , 2000 .

[15]  James B. Rawlings,et al.  Model predictive control with linear models , 1993 .

[16]  Alessandro Brambilla,et al.  Advanced control of chemical processes 2000 (ADCHEM 2000) : a proceedings volume from the IFAC symposium, Pisa, Italy, 14-16 June, 2000 , 2001 .

[17]  M. Reuss,et al.  Evaluation of feeding strategies in carbon‐regulated secondary metabolite production through mathematical modeling , 1981 .

[18]  B. Ripley,et al.  Robust Statistics , 2018, Encyclopedia of Mathematical Geosciences.

[19]  Jay H. Lee,et al.  Model predictive control technique combined with iterative learning for batch processes , 1999 .

[20]  Bart De Moor,et al.  Optimal adaptive control of fed-batch fermentation processes , 1995 .

[21]  David W. Clarke,et al.  Generalized predictive control - Part I. The basic algorithm , 1987, Autom..

[22]  Gábor Szederkényi,et al.  Nonlinear analysis and control of a continuous fermentation process , 2002 .

[23]  D. Bonvin,et al.  Optimization of batch reactor operation under parametric uncertainty — computational aspects , 1995 .

[24]  Ian David Lockhart Bogle,et al.  Robust operation of fed batch fermenters , 1998 .

[25]  T. Brubaker,et al.  Nonlinear Parameter Estimation , 1979 .

[26]  Sten Bay Jørgensen,et al.  Using Continuous Time Stochastic Modelling and Nonparametric Statistics to Improve the Quality of First Principles Models , 2002 .

[27]  Sten Bay Jørgensen,et al.  An Investigation of some Tools for Process Model Identification for Prediction , 2003 .

[28]  G. Bierman,et al.  UDU/T/ covariance factorization for Kalman filtering , 1980 .

[29]  John E. Dennis,et al.  Numerical methods for unconstrained optimization and nonlinear equations , 1983, Prentice Hall series in computational mathematics.

[30]  M. Sørensen,et al.  Martingale estimation functions for discretely observed diffusion processes , 1995 .

[31]  John Matthew Santosuosso,et al.  Dynamic optimization of batch processing , 2003 .

[32]  Heinz Unbehauen,et al.  Some new trends in identification and modeling of nonlinear dynamical systems , 1996 .

[33]  Yonathan Bard,et al.  Nonlinear parameter estimation , 1974 .

[34]  Dominique Bonvin,et al.  Optimal operation of batch reactors—a personal view , 1998 .

[35]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[36]  Jörg Raisch,et al.  Complex Systems - Simple Models? , 2000 .

[37]  Torsten Bohlin,et al.  Issues in nonlinear stochastic grey box identification , 1995 .

[38]  V. Wertz,et al.  Adaptive Optimal Control: The Thinking Man's G.P.C. , 1991 .

[39]  Henrik Madsen,et al.  Estimating Functions for Discretely Observed Diffusions with Measurement Noise , 2000 .

[40]  Richard A. Davis,et al.  Time Series: Theory and Methods , 2013 .

[41]  J. E. Cuthrell,et al.  Simultaneous optimization and solution methods for batch reactor control profiles , 1989 .

[42]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[43]  Sten Bay Jørgensen,et al.  Parameter estimation in stochastic grey-box models , 2004, Autom..

[44]  C. Loan,et al.  Nineteen Dubious Ways to Compute the Exponential of a Matrix , 1978 .

[45]  Peter Young,et al.  Parameter estimation for continuous-time models - A survey , 1979, Autom..

[46]  Sten Bay Jørgensen,et al.  Identification of continuous time models using discrete time data , 2003 .

[47]  Sten Bay Jørgensen,et al.  Computer aided continuous time stochastic process modelling , 2001 .

[48]  M. Powell,et al.  On the Modification of LDL T Factorizations , 1974 .

[49]  Torsten Bohlin,et al.  Issues in Nonlinear Stochastic Grey-Box Identification , 1994 .

[50]  Developing phenomena models from experimental data , 2003 .

[51]  S. Palanki,et al.  Dynamic Optimization of Batch Processes : II . Handling Uncertainty Using Measurements , 2001 .

[52]  Lyle H. Ungar,et al.  A hybrid neural network‐first principles approach to process modeling , 1992 .

[53]  Bo Martin Bibby,et al.  On Estimation for Discretely Observed Diffusions: A Review , 1996 .

[54]  Henrik Madsen,et al.  Applying the EKF to stochastic differential equations with level effects , 2001, Autom..

[55]  M. Sørensen,et al.  Prediction-based estimating functions , 2000 .

[56]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[57]  Henrik Madsen,et al.  VALIDATION OF GREY BOX MODELS , 1993 .

[58]  K. Lim,et al.  Generalized Predictive Control of , 2022 .

[59]  C. Loan.  Computing integrals involving the matrix exponential , 1978 .

[60]  Thomas J. McAvoy,et al.  INTEGRATING NEURAL NETWORKS WITH FIRST PRINCIPLES MODELS FOR DYNAMIC MODELING , 1992 .